@inproceedings{lin-etal-2024-modalities,
title = "Modalities Should Be Appropriately Leveraged: Uncertainty Guidance for Multimodal {C}hinese Spelling Correction",
author = "Lin, Yongliang and
Zhang, Zhen and
Hu, Mengting and
Sun, Yufei and
Zhang, Yuzhi",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1002",
pages = "11463--11474",
abstract = "Chinese spelling correction (CSC) aims to detect and correct spelling errors in Chinese texts. Most spelling errors are phonetically or graphically similar to the correct ones. Thus, recent works introduce multimodal features to obtain achievements. In this paper, we found that different spelling errors have various biases to each modality, highlighting the importance of appropriately exploiting multimodal features. To achieve this goal, we propose the UGMSC framework, which incorporates uncertainty into both the feature learning and correction stages. Specifically, the UGMSC framework makes predictions with multimodal features and estimates the uncertainty of the corresponding modalities. Then it dynamically fuses the features of all modalities for model learning, and performs spelling correction under the uncertainty-guided strategy. Experimental results on three public datasets demonstrate that the proposed approach provides a significant improvement compared with previous strong multimodal models. The proposed framework is model-agnostic and can be easily applied to other multimodal models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lin-etal-2024-modalities">
<titleInfo>
<title>Modalities Should Be Appropriately Leveraged: Uncertainty Guidance for Multimodal Chinese Spelling Correction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yongliang</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhen</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mengting</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yufei</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuzhi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Chinese spelling correction (CSC) aims to detect and correct spelling errors in Chinese texts. Most spelling errors are phonetically or graphically similar to the correct ones. Thus, recent works introduce multimodal features to obtain achievements. In this paper, we found that different spelling errors have various biases to each modality, highlighting the importance of appropriately exploiting multimodal features. To achieve this goal, we propose the UGMSC framework, which incorporates uncertainty into both the feature learning and correction stages. Specifically, the UGMSC framework makes predictions with multimodal features and estimates the uncertainty of the corresponding modalities. Then it dynamically fuses the features of all modalities for model learning, and performs spelling correction under the uncertainty-guided strategy. Experimental results on three public datasets demonstrate that the proposed approach provides a significant improvement compared with previous strong multimodal models. The proposed framework is model-agnostic and can be easily applied to other multimodal models.</abstract>
<identifier type="citekey">lin-etal-2024-modalities</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1002</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>11463</start>
<end>11474</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Modalities Should Be Appropriately Leveraged: Uncertainty Guidance for Multimodal Chinese Spelling Correction
%A Lin, Yongliang
%A Zhang, Zhen
%A Hu, Mengting
%A Sun, Yufei
%A Zhang, Yuzhi
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F lin-etal-2024-modalities
%X Chinese spelling correction (CSC) aims to detect and correct spelling errors in Chinese texts. Most spelling errors are phonetically or graphically similar to the correct ones. Thus, recent works introduce multimodal features to obtain achievements. In this paper, we found that different spelling errors have various biases to each modality, highlighting the importance of appropriately exploiting multimodal features. To achieve this goal, we propose the UGMSC framework, which incorporates uncertainty into both the feature learning and correction stages. Specifically, the UGMSC framework makes predictions with multimodal features and estimates the uncertainty of the corresponding modalities. Then it dynamically fuses the features of all modalities for model learning, and performs spelling correction under the uncertainty-guided strategy. Experimental results on three public datasets demonstrate that the proposed approach provides a significant improvement compared with previous strong multimodal models. The proposed framework is model-agnostic and can be easily applied to other multimodal models.
%U https://aclanthology.org/2024.lrec-main.1002
%P 11463-11474
Markdown (Informal)
[Modalities Should Be Appropriately Leveraged: Uncertainty Guidance for Multimodal Chinese Spelling Correction](https://aclanthology.org/2024.lrec-main.1002) (Lin et al., LREC-COLING 2024)
ACL